Abstract | ||
---|---|---|
Deep neural networks can easily be fooled by an adversary with minuscule perturbations added to an input image. The existing defense techniques suffer greatly under white-box attack settings, where an adversary has full knowledge of the network and can iterate several times to find strong perturbations. We observe that the main reason for the existence of such vulnerabilities is t... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/TPAMI.2020.2978474 | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Keywords | DocType | Volume |
Robustness,Perturbation methods,Training,Linear programming,Optimization,Marine vehicles,Prototypes | Journal | 43 |
Issue | ISSN | Citations |
9 | 0162-8828 | 2 |
PageRank | References | Authors |
0.39 | 7 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Aamir Mustafa | 1 | 14 | 1.29 |
Salman Khan | 2 | 387 | 41.05 |
Munawar Hayat | 3 | 315 | 19.30 |
Roland Goecke | 4 | 1323 | 69.44 |
Jianbing Shen | 5 | 1362 | 60.11 |
Jianbing Shen | 6 | 584 | 33.35 |